Konrad Rieck ๐ŸŒˆ

@rieck.mlsec.org

401 Followers 114 Following

Machine Learning and Security, Professor of Computer Science at TU Berlin,

Paper: LLM-based Vulnerability Discovery through the Lens of Code Metrics
Predicted storm path of Hurricane Katrina
Location of satellite observations and grid points for a prediction step.
Predicted temperature at the peak of the European Heat Wave 2006
SATML Deadline: Sep 24
IEEE Conference on Secure and Trustworthy Machine Learning Technical University of Munich, Germany March 23โ€“25, 2026
Visualization of a matrix mutplication. The matrices are decomposed into blocks that are processed individually.
Visualization of the attack. A dog is shown for which three backends yield the prediction "boxer", while one backend returns "castle".
Call for Competitions Competition proposal deadline: August 6, 2025 Decision notification: August 27, 2025
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), March 23-25, 2025, Munich Submission deadline: September 24, 2025
Members of the MLSEC team (mlsec.org)
Audience at SaTML 2025
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), April 9-11, 2025, Copenhagen.
Left: Box-plot of the parameter distribution in the final layer before and after backdoor insertion. Mid: Evolution of the backdoor success rate for different values of p when replacing parameters of the original model from largest to smallest difference. Right: Evolution of the backdoor success rate for p= 1 and different regularization strengths ฮป.
Overview of our hardware-based backdoor attack.
Michael Veale
Call for Papers: SaTML. Deadline: September 18, 2024